基于反向特征消除的ELM盾构机故障诊断
基于反向特征消除的ELM盾构机故障诊断
摘要
随着全世界人均生存空间的不断减少，人类发明了各种设备来扩展生存空间，其中最具有代表性的机械便是盾构机。盾构机是一种具有多系统、多驱动源的复杂大型隧道掘进装备。但是由于它的结构比较复杂、工作环境相对比较封闭，盾构机在工作过程中极易发生各种故障，封闭的结构让盾构机的修理工作及其困难。由此，需要一种可以在第一时间甚至在故障发生前便能预测故障发生部位的方法，来提高工作效率，减少经济损失。
本文将神经网络与盾构机相结合，构造一种新式的基于神经网络的盾构机故障诊断系统。
为了提高盾构机故障诊断的准确性及效率，提出了基于反向特征消除的ELM盾构机故障诊断方法。针对盾构机运行数据维数多、数量大的特点，引入反向特征消除（Reverse feature elimination，RFE）方法进行数据降维，消除冗余维度，解除特征间的相关性。考虑到神经网络故障诊断速度慢且效率低，基于极限学习机构建了ELM神经网络分类器模型进行盾构机故障诊断。基于现场施工数据的仿真结果表明，该方法显著提高了盾构机故障诊断的精度和效率，具有良好的工程应用价值。
关键词：盾构机、故障诊断、极限学习机、反向特征消除
Fault diagnosis of ELM shield machine based on reverse
feature elimination
ABSTRACT
With the continuous reduction of living space per capita in the world, human beings have invented various devices to expand living space, among which the most representative machine is shield machine.Shield machine is a kind of complex large-scale tunneling equipment with multiple systems and multiple driving sources. However, due to its complex structure and relatively closed working environment, the shield machine is prone to various failures in the process of work. The closed structure makes the repair work of the shield machine very difficult. Therefore, we need a method that can predict the location of the fault in the first time or even before the fault occurs, to improve work efficiency and reduce economic losses.
In this paper, neural network and shield machine are combined to construct a new fault diagnosis system of shield machine based on neural network.
In order to improve the accuracy and efficiency of shield machine fault diagnosis, a fault diagnosis met
hod based on ELM is proposed. In view of the characteristics of shield machine operation data with many dimensions and large quantity, the reverse feature elimination (RFE) method is introduced to reduce the dimension of data, eliminate the redundant dimension and remove the correlation between features. Considering the slow speed and low efficiency of neural network fault diagnosis, the ELM neural network classifier model is built based on the limit learning mechanism for shield machine fault diagnosis. The simulation results based on the field construction data show that the method improves the accuracy and efficiency of shield machine fault diagnosis significantly, and has good engineering application value.
KEYWORDS: shield machine, fault diagnosis, limit learning machine,reverse feature elimination
目录
1 绪论 (1)
1.1 研究背景 (1)
1.2 盾构掘进系统国内外研究与发展现状 (1)
1.2.1 国外盾构掘进系统的发展状况 (1)
1.2.2 国内盾构掘进系统的发展状况 (3)
1.3 盾构掘进系统故障诊断的现状 (4)
1.4 论文结构安排 (6)
1.5 本章小结 (7)
2盾构机简介及故障模式的研究 (8)
2.1盾构机简介 (8)
2.2 盾构机的主要子系统 (8)
2.3盾构掘进系统掘进工作流程 (11)
2.4 盾构机常见故障及其分析 (13)
2.5本章小结 (14)
3基于ELM神经网络的盾构机故障诊断 (15)
3.1盾构机故障类型确定与故障数据的获取及处理 (15)
3.2基于BP神经网络的盾构掘进系统故障诊断 (17)
3.2.1 BP神经网络 (17)
3.2.2基于BP神经网络的盾构机故障诊断模型的建立 (17)
3.2.3仿真研究与分析 (19)
英吉利海峡海底隧道
3.3基于ELM神经网络的盾构掘进系统故障诊断 (21)
3.3.1 ELM神经网络 (22)
3.3.2基于ELM神经网络的盾构机故障诊断模型的建立 (23)
3.3.3仿真研究与分析 (25)
3.4对比分析 (27)
3.5 本章小结 (28)
4 基于反向特征消除的ELM盾构机故障诊断 (29)
4.1基于反向特征消除的BP盾构机故障诊断 (29)
4.1.1基于反向特征消除的BP盾构机故障诊断模型的建立 ..29
4.1.2仿真研究与分析 (32)
4.2基于反向特征消除的ELM盾构掘进系统故障诊断 (33)
4.2.1基于反向特征消除的ELM盾构机故障诊断模型的建立
(33)
4.2.2仿真研究与分析 (36)
4.3对比分析 (38)
4.3.1四种算法的准确率对比分析 (39)
4.3.2四种算法的综合性对比分析 (40)
4.4本章小结 (41)
5 总结与展望 (43)
参考文献 (46)
致谢 (53)
攻读学位期间发表的学术论文目录 (54)

版权声明：本站内容均来自互联网，仅供演示用，请勿用于商业和其他非法用途。如果侵犯了您的权益请与我们联系QQ:729038198，我们将在24小时内删除。